Local binary CNN processing method, device, storage medium and processor

A technology of local binarization and processing methods, applied in the field of convolutional neural networks, can solve problems such as low operating efficiency

Inactive Publication Date: 2017-12-19
珠海习悦信息技术有限公司
View PDF2 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a processing method, device, storage medium, and processor of a locally binarized CNN,...

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Local binary CNN processing method, device, storage medium and processor
  • Local binary CNN processing method, device, storage medium and processor
  • Local binary CNN processing method, device, storage medium and processor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] According to an embodiment of the present invention, an embodiment of a local binarization CNN processing method is provided. It should be noted that the steps shown in the flow chart of the accompanying drawings can be implemented in a computer system such as a set of computer-executable instructions and, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

[0028] Fig. 1 (a) is a schematic flow chart of an optional local binarized CNN processing method according to an embodiment of the present invention, as shown in Fig. 1 (a), the method includes the following steps:

[0029] Step S102, training the first convolutional neural network according to the preset data set to obtain the second convolutional neural network;

[0030] Step S104, replacing all convolutional layer units in the first convolutional neural network with local binarized convolutiona...

Embodiment 2

[0083] According to another aspect of the embodiments of the present invention, a local binarization CNN processing device is also provided, such as Figure 5 As shown, the device includes: a first training unit 501 , a first replacement unit 503 , a second replacement unit 505 , a processing unit 507 , and a second training unit 509 .

[0084] Among them, the first training unit 501 is used to train the first convolutional neural network according to the preset data set to obtain the second convolutional neural network; the first replacement unit 503 is used to convert all convolutional neural networks in the first convolutional neural network to The multilayer unit is replaced by a local binarized convolution unit to obtain the third convolutional neural network; the second replacement unit 505 is used to replace the target fully connected layer in the third convolutional neural network with a group connection layer, thereby Obtain the fourth convolutional neural network, wh...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a local binary CNN processing method, a device, a storage medium and a processor, wherein the method comprises the steps of training a first convolutional neural network according to a preset data set, and obtaining a second convolutional neural network; replacing all convolutional layer units in the first convolutional neural network by a local binary convolutional unit, thereby obtaining a third convolutional neural network; replacing objective total connecting layers in the third convolutional neural network by a grouping connecting layer, thereby obtaining a fourth convolutional neural network, wherein the objective total connecting layers are all total connecting layers except for a bottom classification layer in the third convolutional neural network; initializing the fourth convolutional neural network, thereby obtaining a fifth convolutional neural network; and training the fifth convolutional neural network based on the second convolutional network and a preset data set, thereby obtaining an objective convolutional neural network. The local binary CNN processing method, the device, the storage medium and the processor settle a technical problem of relatively low operation efficiency in the local binary convolutional neural network in prior art.

Description

technical field [0001] The present invention relates to the field of convolutional neural networks, in particular to a processing method, device, storage medium and processor for local binarization CNN. Background technique [0002] With the popularity of deep learning, more and more convolutional neural network technologies have entered the application stage. Convolutional neural networks have demonstrated superior performance in various tasks such as image recognition, object detection, and scene classification with deep-level, high-dimensional model architectures. However, in the localization application of the terminal platform, the convolutional neural network is facing huge challenges. It has a large number of parameters and complex calculations, and it is difficult to adapt to the embedded terminal platform with limited storage and computing resources. [0003] In recent years, a lot of research has been done on low-precision binary convolutional neural networks. The...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/62G06K9/46G06N3/04
CPCG06V10/40G06V10/467G06N3/048G06N3/045G06F18/214
Inventor 王志鹏周文明
Owner 珠海习悦信息技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap